---
license: apache-2.0
base_model: Efficient-Large-Model/Sana_1600M_512px
pipeline_tag: text-to-image
library_name: mlx
tags:
  - sana
  - mlx
  - apple-silicon
  - quantization
  - ternary
  - clark-air
---

# Clark Air · Sana 1.6B · MLX 2-bit

The Clark Air Sana 1.6B transformer quantized to **ternary, stored in MLX 2-bit kernels** for
Apple Silicon — the first MLX port of Sana. **543 MB** vs 3.21 GB FP16.

![sample — generated end-to-end on Apple Silicon (MLX 2-bit)](sample.png)

*Generated end-to-end on an M5 Max: MLX 2-bit transformer driving the denoising loop, VAE decode.*

## Contents
- `clark_air_sana_mlx_2bit.safetensors` — MLX-quantized transformer (trunk ternary in MLX 2-bit
  slots at per-layer power-of-two groups; conditioning/projection layers kept high-precision).
- `mlx_sana.py` — the MLX runtime / loader.

## Status
The **transformer** (the compressed core), verified to reproduce the FP16 model across a full
20-step generation (3.4% per-step). A full standalone MLX pipeline (scheduler + text encoder +
VAE) is in progress; until then run the transformer with the rest of the Sana pipeline bridged
from `diffusers`.

## Usage
```python
import mlx.core as mx
from mlx_sana import SanaMLX
sd = mx.load("clark_air_sana_mlx_2bit.safetensors")
model = SanaMLX(sd)  # auto-detects the packed 2-bit trunk
# noise = model(latent, encoder_hidden_states, timestep, enc_mask=mask)
```

## License
Apache-2.0 © Clark Labs, Inc.